Modelling Context Dependency in Acoustic-Phonetic and Lexical Representations.

摘要

In 1989, our group first reported on the development of SUMMIT, a segment-based speaker-independent continuous-speech recognition system. The initial version of SUMMIT made use of fairly simple context-independent models for the lexical labels. Recently, we have begun to incorporate more complex models of lexical labels that take into account a variety of contextual factors. These changes, along with an improved corrective training procedure for adapting pronunciation arc weights and a larger set of training data, have resulted in the reduction of error rate by almost a factor of two on the Resource Management task.